Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2175 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.3771. Min Act: 0.0000

Data Index: 971381 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1405327 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.2088. Min Act: -0.0000

Data Index: 581775 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.2913. Min Act: 0.0000

Data Index: 1294378 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1238068 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1403. Min Act: 0.0000

Data Index: 1257847 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1195311 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1176. Min Act: -0.0000

Data Index: 54115 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1255. Min Act: -0.0000

Data Index: 270971 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0579. Min Act: 0.0000

Data Index: 1684785 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1579318 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1322132 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0587. Min Act: -0.0000

Data Index: 821806 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1985781 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0505. Min Act: -0.0000

Data Index: 232779 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1864273 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0975. Min Act: -0.0000

Data Index: 133853 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1818286 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1330306 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1767991 (The Pile)

Max Activating Token Index: 429